One-Shot Structure-Aware Stylized Image Synthesis
This addresses the challenge of maintaining image structure during stylization for applications in computer vision and graphics, representing an incremental improvement over existing diffusion-based methods.
The paper tackles the problem of structure preservation in image stylization by proposing OSASIS, a one-shot method that effectively disentangles semantics from structure, allowing control over content and style levels, and it outperforms other methods, especially for rarely encountered input images.
While GAN-based models have been successful in image stylization tasks, they often struggle with structure preservation while stylizing a wide range of input images. Recently, diffusion models have been adopted for image stylization but still lack the capability to maintain the original quality of input images. Building on this, we propose OSASIS: a novel one-shot stylization method that is robust in structure preservation. We show that OSASIS is able to effectively disentangle the semantics from the structure of an image, allowing it to control the level of content and style implemented to a given input. We apply OSASIS to various experimental settings, including stylization with out-of-domain reference images and stylization with text-driven manipulation. Results show that OSASIS outperforms other stylization methods, especially for input images that were rarely encountered during training, providing a promising solution to stylization via diffusion models.